A First-Occupancy Representation for Reinforcement Learning

Abstract

Both animals and artificial agents benefit from state representations that support rapid transfer of learning across tasks and which enable them to efficiently traverse their environments to reach rewarding states. The successor representation (SR), which measures the expected cumulative, discounted state occupancy under a fixed policy, enables efficient transfer to different reward structures in an otherwise constant Markovian environment and has been hypothesized to underlie aspects of biological behavior and neural activity. However, in the real world, rewards may move or only be available for consumption once, may shift location, or agents may simply aim to reach goal states as rapidly as possible without the constraint of artificially imposed task horizons. In such cases, the most behaviorally-relevant representation would carry information about when the agent was likely to first reach states of interest, rather than how often it should expect to visit them over a potentially infinite time span. To reflect such demands, we introduce the first-occupancy representation (FR), which measures the expected temporal discount to the first time a state is accessed. We demonstrate that the FR facilitates exploration, the selection of efficient paths to desired states, allows the agent, under certain conditions, to plan provably optimal trajectories defined by a sequence of subgoals, and induces similar behavior to animals avoiding threatening stimuli.

References in corpus (8)

• Continuous control with deep reinforcement learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Deep Successor Reinforcement Learning
• Environment-Independent Task Specifications via GLTL
• Provably efficient RL with Rich Observations via Latent State Decoding
• Better transfer learning with inferred successor maps
• APS: Active Pretraining with Successor Features
• URLB: Unsupervised Reinforcement Learning Benchmark